Workload Prediction for Cloud Cluster Using a Recurrent Neural Network

Weishan Zhang, Bo Li, Dehai Zhao, Faming Gong, Q. Lu
{"title":"Workload Prediction for Cloud Cluster Using a Recurrent Neural Network","authors":"Weishan Zhang, Bo Li, Dehai Zhao, Faming Gong, Q. Lu","doi":"10.1109/IIKI.2016.39","DOIUrl":null,"url":null,"abstract":"Maximizing benefits from a cloud cluster with minimum computational costs is challenging. An accurate prediction to cloud workload is important to maximize resources usage in the cloud environment. In this paper, we propose an approach using recurrent neural networks (RNN) to realize workload prediction, where CPU and RAM metrics are used to evaluate the performance of the proposed approach. In order to obtain optimized parameter set, an orthogonal experimental design is conducted to find the most influential parameters in RNN. The experiments with Google Cloud Trace data set shows that the RNN based approach can achieve high accuracy of workload prediction, which lays a good foundation for optimizing the running of a cloud computing environment.","PeriodicalId":371106,"journal":{"name":"2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"33","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IIKI.2016.39","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 33

Abstract

Maximizing benefits from a cloud cluster with minimum computational costs is challenging. An accurate prediction to cloud workload is important to maximize resources usage in the cloud environment. In this paper, we propose an approach using recurrent neural networks (RNN) to realize workload prediction, where CPU and RAM metrics are used to evaluate the performance of the proposed approach. In order to obtain optimized parameter set, an orthogonal experimental design is conducted to find the most influential parameters in RNN. The experiments with Google Cloud Trace data set shows that the RNN based approach can achieve high accuracy of workload prediction, which lays a good foundation for optimizing the running of a cloud computing environment.
基于递归神经网络的云集群工作负荷预测
以最小的计算成本最大化云集群的好处是一项挑战。准确预测云工作负载对于最大限度地利用云环境中的资源非常重要。在本文中,我们提出了一种使用递归神经网络(RNN)来实现工作负载预测的方法,其中CPU和RAM指标用于评估所提出方法的性能。为了得到最优的参数集,通过正交实验设计找出对RNN影响最大的参数。谷歌Cloud Trace数据集的实验表明,基于RNN的方法可以实现较高的工作负载预测精度,为优化云计算环境的运行奠定了良好的基础。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信